Poster Presentation Presented at the 2019 Rising Stars in EECS Workshop

RBM Image Generation Using the D-Wave 2000Q

, , and

We describe a hybrid approach that combines a deep convolutional neural network autoencoder and a quantum Restricted Boltzmann Machine (RBM) for image generation using the D-Wave 2000Q. We compare the quantum learned distribution with the classical learned distribution, and quantify the quantum effects on latent representations.


  • 2485385 bytes

Misc

Downloads: 538 downloads

UMBC ebiquity